Authors:
Nguyen Duc Tang Tri
;
Vu Quang
and
Kokolo Ikeda
Affiliation:
JAIST, Japan
Keyword(s):
Deep Learning, Fighting Game, Convolutional Neural Network.
Related
Ontology
Subjects/Areas/Topics:
Artificial Intelligence
;
Biomedical Engineering
;
Biomedical Signal Processing
;
Computational Intelligence
;
Evolutionary Computing
;
Health Engineering and Technology Applications
;
Human-Computer Interaction
;
Knowledge Discovery and Information Retrieval
;
Knowledge-Based Systems
;
Machine Learning
;
Methodologies and Methods
;
Neural Networks
;
Neurocomputing
;
Neurotechnology, Electronics and Informatics
;
Pattern Recognition
;
Physiological Computing Systems
;
Sensor Networks
;
Signal Processing
;
Soft Computing
;
Symbolic Systems
;
Theory and Methods
Abstract:
Deep Learning has become most popular research topic because of its ability to learn from a huge amount of data. In recent research such as Atari 2600 games, they show that Deep Convolutional Neural Network (Deep CNN) can learn abstract information from pixel 2D data. After that, in VizDoom, we can also see the effect of pixel 3D data in learning to play games. But in all the cases above, the games are perfect-information games, and these images are available. For imperfect-information games, we do not have such bit-map and moreover, if we want to optimize our model by using only important features, then will Deep CNN still work? In this paper, we try to confirm that Deep CNN shows better performance than usual Neural Network (usual NN) in modeling Game Agent. By grouping important features, we increase the accuracy of modeling strong AI from 25.58% with a usual neural network to 54.24% with our best CNN structure.